Analysing automatic descriptions of intonation with ICARUS

We present ICARUS for intonation ‐ a graphical tool which allows to access automatically derived F0 features in an intuitive and user-friendly way. It can be used for data exploration and search. Tonal features can be accessed together with information from other linguistic levels; this is exemplified in two search queries where we combine the search for a specific tonal contour with a) coreference annotations and b) automatically derived syntactic annotations. Thereby we demonstrate how ICARUS for intonation bridges the gap between manual/semiautomatic analysis of relatively small, manually annotated data sets and automatic analysis of larger corpora with automatically derived features. Index Terms: Intonation, parametric F0 analysis, multi-level annotations, syntax interface, semantic interface

[1]  Bhuvana Ramabhadran,et al.  Discriminative training and unsupervised adaptation for labeling prosodic events with limited training data , 2010, INTERSPEECH.

[2]  Julia Hirschberg,et al.  Automatic ToBI prediction and alignment to speed manual labeling of prosody , 2001, Speech Commun..

[3]  Jonas Kuhn,et al.  A Graphical Interface for Automatic Error Mining in Corpora , 2014, EACL.

[4]  Kerstin Eckart,et al.  A Discourse Information Radio News Database for Linguistic Analysis , 2012, Linked Data in Linguistics.

[5]  Antje Schweitzer,et al.  Experiments on automatic prosodic labeling , 2009, INTERSPEECH.

[6]  Mats Rooth A theory of focus interpretation , 1992, Natural Language Semantics.

[7]  Gregor Möhler Describing intonation with a parametric model , 1998, ICSLP.

[8]  Arndt Riester,et al.  Using prosodic annotations to improve coreference resolution of spoken text , 2015, ACL.

[9]  Arndt Riester,et al.  Anarchy in the NP. When new nouns get deaccented and given nouns don’t , 2015 .

[10]  Daniel Büring,et al.  Semantics, Intonation and Information Structure , 2007 .

[11]  Stefan Baumann,et al.  Coreference, lexical givenness and prosody in German , 2013 .

[12]  Anton Batliner,et al.  Consistency in transcription and labelling of German intonation with GToBI , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[13]  Andrew Rosenberg,et al.  AutoBI - a tool for automatic toBI annotation , 2010, INTERSPEECH.

[14]  Anders Björkelund,et al.  The Extended DIRNDL Corpus as a Resource for Coreference and Bridging Resolution , 2014, LREC.

[15]  Jonas Kuhn,et al.  ICARUS - An Extensible Graphical Search Tool for Dependency Treebanks , 2013, ACL.

[16]  Gregor Mohler Improvements of the PaIntE model for F_0 parametrization , 2001 .

[17]  Michael Wagner,et al.  Givenness and Locality , 2006 .

[18]  Julia Hirschberg,et al.  Deaccentuation of Words Representing ‘Given’ Information: Effects of Persistence of Grammatical Function and Surface Position , 1994 .

[19]  Jonas Kuhn,et al.  Visualization, Search, and Error Analysis for Coreference Annotations , 2014, ACL.

[20]  C. Reiss,et al.  The Oxford Handbook of Linguistic Interfaces , 2007 .

[21]  Shrikanth Narayanan,et al.  Detecting prominence in conversational speech: pitch accent, givenness and focus , 2008, Speech Prosody 2008.